© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 72376
    Prev
    Next
    INDEX
    Explanations

    confidence and related concepts

    np_acts-logits-general · gemini-2.5-flash-lite

    potential deficiency and preparation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ים
    0.52
     cerc
    0.49
     detectable
    0.49
    ขั้นตอน
    0.49
    ો
    0.49
     discernible
    0.47
    modus
    0.47
    𝙘
    0.46
     agon
    0.46
    先の
    0.45
    POSITIVE LOGITS
     मोटापा
    0.44
    ၀
    0.42
     মহামার
    0.41
     गरजेचे
    0.41
     Tourism
    0.40
     کرے
    0.40
     Safegu
    0.40
     Hospitality
    0.39
     бассей
    0.39
    Tourism
    0.39
    Activations Density 0.001%

    No Known Activations